Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection
Bo Zhang, Jiakang Yuan, Botian Shi, Tao Chen, Yikang Li, Yu Qiao
Abstract
XYZ Z []^_ ab [c]d[] [c] e ``d[g hi g g jkh e kh [] m h n[ce oc] Z ke ] [h ] e kde lfpjqe cqi m ] [kc[hkh[Z e Yhd[] [c] e kcrdZ njq[] q[rkZ [ de Z [c] g rd[ng r[de ] q[Zdk] kh [] st ] qe hnkn[Z pj[ h ] Ydr] q[] kh ui] Z ke o[d^_d[] [c] Zi Z ffYg m ] e ng [dk] kh [] h sv[ah [Z w[] qk]] qe hknn[kZ h] a[kcqkg m g [] kh upjqe cqe hfke rdY[] ] qk]] q[h [dk] kh [] h nZ [h []hYah ] k] e kgdk] km g [w[gde i i [Z [ kxfrm g [w[gwkZ e k] e ye _z] rn[hk] k kc|Ye h e ] e ] kdh st ne Z [darhYcqah [Z wk] e k^_jqe cqg [w[Z kl[hkhe fng [dk] km g [w[gcZ m Z [c] e n[Z k] e e cm g [w[gcYng e kZ [cYng e dYg [] kg g [we k] [] q[Ye dkag [dk] km g [w[gk] kxfrm g [w[gde i i [Z [ e w[g r s YZ f[] qde hh e fng [k qfk^_ab [c] d[] [c] e q[f][i i [c] e w[g rg [kZ Z ffYg ] e ng [i i m ] q[m h q[g i ^dk] kh [] h] a] ke `Z [de h cZ e fe ] e w[k k] e `sxn[Z e f[] hkZ [c`] [d`dk] kh []cg e dk] e ] e sq[e ZZ [h Yg ] hd[f] Z k] [ ] qk]^[xc[[dhkh[Z e [hie we dYkgd[] [c] Z h] Z ke [d kh [] pje ] qks nkZ kf[] [Ze [dakh [g e [d[] [c]Z sv[[xn[c]] qe hjZ uje g ge h ne Z [] q[Z [h [kZ cqi^_l[[Z kg e k] e je g gnYh q ] q[g e fe ] hin[Z c[n] Ykgn[Z i `Z fk ¡¢£s ¤¥¦ 1 9 2 1
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers20
- EMR-Merging: Tuning-Free High-Performance Model MergingChenyu Huang, Peng Ye, Tao Chen, Tong He et al.NeurIPS 2024 · 134 citations
- Uni3DETR: Unified 3D Detection TransformerZhenyu Wang, Ya-Li Li, Xi Chen, Hengshuang Zhao et al.NeurIPS 2023 · 65 citations
- Towards Large-Scale 3D Representation Learning with Multi-Dataset Point Prompt TrainingXiaoyang Wu, Zhuotao Tian, Xin Wen, Bohao Peng et al.CVPR 2024 · 39 citations
- AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud DatasetJiakang Yuan, Bo Zhang, Xiangchao Yan, Botian Shi et al.NeurIPS 2023 · 36 citations
- DriveWorld: 4D Pre-Trained Scene Understanding via World Models for Autonomous DrivingChen Min, Dawei Zhao, Liang Xiao, Jian Zhao et al.CVPR 2024 · 20 citations
Related papers
- Benchmark Platform for Ultra-Fine-Grained Visual Categorization Beyond Human PerformanceXiaohan Yu, Yang Zhao, Yongsheng Gao, Xiaohui Yuan et al.ICCV 2021 · 37 citations
- MOHO: Learning Single-View Hand-Held Object Reconstruction with Multi-View Occlusion-Aware SupervisionChenyangguang Zhang, Guanlong Jiao, Yan Di, Gu Wang et al.CVPR 2024 · 5 citations
- Towards Backward-Compatible Continual Learning of Image CompressionZhihao Duan, Ming Lu, Justin Yang, Jiangpeng He et al.CVPR 2024
- Subversion-resilient Key-exchange in the Post-quantum WorldKévin Duverger, Pierre-Alain Fouque, Charlie Jacomme, Guilhem Niot et al.CCS 2025
- Cross Copy Network for Dialogue GenerationChangzhen Ji, Xin Zhou, Yating Zhang, Xiaozhong Liu et al.EMNLP 2020 · 11 citations
